Cisco Technology, Inc.

Arch Rock Corporation

Jonathan W Hui

Jean-Philippe Vasseur

Wei Hong

David E Culler

Alec Woo

Lik Chuen Alec Woo

Sukrit Dasgupta

Grégory Mermoud

Shmuel Shaffer

Atul Mahamuni

Navindra Yadav

Jeongyeup Paek

Andrea Di Pietro

Javier Cruz Mota

Stefano Benedetto Previdi

Gilman Tolle

Philip Buonadonna

Krishna Kondaka

Anjum Ahuja

Pascal Thubert

Patrick Wetterwald

Ralph Droms

Sandeep Shetty

Navneet Agarwal

Nitin Nayar

Paul Bernard Duffy

Karthikeyan Ganesan

Vikram Jayaraman

Raja Rajaram Kannan

In one embodiment, asynchronous broadcast communication is performed based on time-based events in channel-hopping networks. The embodiments include determining a plurality of channels in a channel-hopping network, on which a plurality of nodes communicate, and identifying an asynchronous broadcast message to transmit from a particular node. A plurality of time-based events is determined, and in response to each time-based event, the asynchronous broadcast message is transmitted on a single selected channel of the plurality of channels per time-based event.

Asynchronous broadcast communication based on time-based events in channel-hopping networks

In one embodiment, a device in a network identifies one or more traffic classes used by one or more nodes in the network. The device determines routing requirements for a particular traffic class of the one or more traffic classes. The device generates a channel assignment that assigns the particular traffic class to a particular channel based on the routing requirements for the particular traffic class. The device provides the channel assignment to the one or more nodes. The one or more nodes use the channel assignment to route traffic of the particular traffic class within the network.

Traffic class capacity allocation in computer networks

In one embodiment, a device in a network detects a power outage event. The device monitors one or more operational properties of the device, in response to detecting the power outage event. The device determines whether to initiate a traffic control mechanism based on the one or more monitored operational properties of the device, according to a power outage traffic control policy. The device causes one or more nodes in the network that send traffic to the device to regulate the traffic sent to the device, in response to a determination that the traffic control mechanism should be initiated.

Network traffic control during limited power situations

In one embodiment, a device receives a router advertisement message after a power outage event in a network. The device joins the network, in response to receiving the router advertisement message. The device sends a power restoration notification message via the network. The device selectively delays a disconnected node from joining the network.

Phased network formation for power restoration

In one embodiment, a device in a network identifies an upcoming network formation event. The device instructs one or more nodes in the network to use a network formation broadcast schedule during the event. The device determines that a degree of functionality in the network during the event exceeds a threshold amount. The device instructs the one or more nodes to use a normal broadcast schedule, in response to determining that the degree of functionality in the network during the event exceeds the threshold amount. Channels of the network formation broadcast schedule are active more frequently than channels of the normal broadcast schedule when in use.

Proactive broadcast capacity adjustment for fast network joins

In one embodiment, a device in a network determines that one or more network nodes should use a stateful address configuration protocol to obtain network addresses. The device causes the one or more network nodes to use the stateful address configuration protocol, in response to determining that the one or more nodes should use the stateful address configuration protocol to obtain network addresses. The device determines that the one or more network nodes should use a stateless address configuration protocol to obtain network addresses. The device causes the one or more network nodes to use the stateless address configuration protocol, in response to determining that the one or more nodes should use the stateless address configuration protocol to obtain network address.

Optimizing global IPv6 address assignments

In a multi-PHY, low power and lossy network comprising a plurality of nodes, a sender determines that a dwell time threshold limit for transmission of data will be exceeded by transmission of the data over a first network interface or that the recipient is unknown. The sender determines transmission parameters for the transmission of the data over the first network interface and transmits the transmission parameters to a receiver device over a second network interface that is different than the first network interface. The sender determines a channel on the first network interface for transmission of the data and transmits the determined channel with the transmission parameters to the receiver, or the receiver determines the channel on the first network interface for transmission of the data and transmits an indication of the determined channel to the sender in response to receiving the transmission parameters.

Obtaining data reception parameters on-demand in a multiple interface network

In one embodiment, data packet messages are received in a Field Area Router (FAR) sent from one or more sources toward one or more destination devices in a Low-Power Lossy Network (LLN). An LLN routing topology for the data packet messages is interpolated in the FAR. An expected time for the data packet messages to reach a destination device in the LLN is determined based upon the routing topology interpolation. Traffic shaping is applied by the FAR for the data packet messages based upon the determined expected time for the data packet messages to reach destination devices in the LLN.

Network traffic shaping for low power and lossy networks

In one embodiment, a learning machine may be used to select observer nodes in a LLN such that the liveness of one or more nodes of interest may be monitored indirectly. In particular, a management device may receive network data on one or more network traffic parameters of a computer network. The management device may then determine, based on the network data, a candidate list of potential observer nodes to monitor activity or inactivity of one or more subject nodes. The management device may then dynamically select, using a machine learning model, a set of optimized observer nodes from the candidate list of potential observer nodes.

Monitoring node liveness in low-power lossy networks

The techniques herein improve the performance of Trickle-based asynchronous broadcasts in a channel-hopping network, such as a low-power and lossy network (LLN). In particular, a plurality of channels in a channel-hopping network on which a plurality of nodes communicate is determined, and an asynchronous broadcast message is identified to transmit from a particular node. Additionally, a plurality of time-based events is determined, and in response to each time-based event, the asynchronous broadcast message is transmitted on a single selected channel of the plurality of channels per time-based event.

In one embodiment, a device in a network detects a bidirectional traffic flow along a primary path in the network. The device determines that a self-interference condition exists along the primary path. The device selects an alternate path in the network. The device causes the traffic flow to use the primary path for packets of the traffic flow sent in a first direction and to use the alternate path for packets of the traffic flow send in a second direction that is opposite that of the first direction.

Optimizing bidirectional traffic flows

In one embodiment, a sender in a shared-communication network determines whether a pending frame is low-latency or high-throughput, and sets a maximum transmission unit (MTU) of the pending frame as a first MTU in response to a low-latency frame and a longer second MTU in response to a high-throughput frame. In another embodiment, a receiver receives a data frame from a sender according to an MTU, and determines a trigger for adjusting the MTU based on latency requirements. In response to the trigger, the receiver sets an interrupt flag in a link-layer acknowledgment for the received data frame. In still another embodiment, a sender determines a pending low-latency data frame to send to a receiver operating according to an MTU, and sends a control message to the receiver to indicate the pending low-latency data frame and an adjusted MTU.

Dynamically adjusting frame MTU to support low-latency communication

In one embodiment, a device in a network identifies a routing domain migration candidate node in a first routing domain that is in range of a second routing domain. The device determines that the second routing domain is able to accommodate the candidate node sending traffic via the second routing domain. The device determines that the candidate node should send traffic via the second routing domain, based in part on a determination that the second routing domain is able to accommodate the candidate node sending traffic via the second routing domain. The device causes the candidate node to send traffic via the second routing domain.

Dynamic capacity-based routing domain load balancing

In one embodiment, a device in a network determines a first channel hopping schedule for the device to receive unicast communications from one or more neighbors of the device. The first channel hopping schedule differs from channel hopping schedules used by the one or more neighbors to receive unicast communications. The device determines a second channel hopping schedule for the device that includes a common channel that is common to the device and the one or more neighbors at any given point in time, wherein the second channel hopping schedule is self-generated by each of the device and the one or more neighbors. The device switches from the first channel hopping schedule to the second channel hopping schedule, in response to a network event. The device causes a particular neighbor to join the network using the second channel hopping schedule.

Growing community of inventors

Belmont, CA, United States of America

Jonathan W Hui